CN114548494A - Visual cost data prediction intelligent analysis system - Google Patents
Visual cost data prediction intelligent analysis system Download PDFInfo
- Publication number
- CN114548494A CN114548494A CN202210034764.7A CN202210034764A CN114548494A CN 114548494 A CN114548494 A CN 114548494A CN 202210034764 A CN202210034764 A CN 202210034764A CN 114548494 A CN114548494 A CN 114548494A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- intelligent
- value
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 46
- 230000000007 visual effect Effects 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 104
- 230000008569 process Effects 0.000 claims abstract description 75
- 238000004364 calculation method Methods 0.000 claims abstract description 50
- 238000010276 construction Methods 0.000 claims abstract description 50
- 238000013528 artificial neural network Methods 0.000 claims abstract description 39
- 238000012216 screening Methods 0.000 claims abstract description 25
- 238000007726 management method Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000013524 data verification Methods 0.000 claims abstract description 9
- 238000004519 manufacturing process Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 14
- 238000013473 artificial intelligence Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 7
- 238000011084 recovery Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000008676 import Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000003754 machining Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 7
- 238000007405 data analysis Methods 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000010835 comparative analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A visual intelligent analysis system for cost data prediction comprises a data acquisition system, a data verification module, a screening matching module, an intelligent data processing unit and a BIM calculation unit, the output end of the data acquisition system is respectively connected with the input ends of the data verification module and the screening matching module, the output end of the data verification module is connected with the input end of the data intelligent processing unit, the output end of the data intelligent processing unit is respectively connected with the input ends of the BIM calculation unit and the screening matching module, the output end of the screening matching module is connected with the input end of the neural network prediction unit, the output ends of the BIM calculation unit and the neural network prediction unit are respectively connected with the input end of the analysis decision unit, and the output end of the analysis decision unit is connected with the input end of the monitoring management unit. The design not only improves the data analysis capability of the construction cost process, but also improves the prediction precision.
Description
Technical Field
The invention relates to the technical field of engineering cost data processing, in particular to a visual cost data prediction intelligent analysis system which is mainly suitable for improving the cost process data analysis capability.
Background
The engineering cost is the comprehensive application of knowledge and skills in management, economics, engineering technology and other aspects, the working process of predicting, planning, controlling, accounting, analyzing and evaluating the engineering cost is called engineering cost management, according to the procedures, methods and basis specified by laws, regulations and standards, the prediction or determination of the engineering cost and the constituent content thereof is called engineering pricing, the engineering pricing basis includes the engineering metering pricing standard, engineering pricing quota and engineering cost information related to pricing content, pricing method and price standard, etc., the engineering cost pricing prediction generally takes fuzzy mathematics, grey system, neural network and the like as the theoretical basis, and establishes a relevant model for the actual engineering to predict the cost. The artificial neural network is an artificial intelligence technology for simulating the structure of a biological nervous system, which is popular in recent years, can automatically learn previous experiences from data samples without complex query and expression processes, can automatically approximate functions which best describe the rule of sample data, and reveals the nonlinear relation contained in the data samples.
In the forecast analysis based on the visualized construction cost data, the forecast is a relatively complex system, which comprises a plurality of influencing factors, and a plurality of uncertain factors are also contained in the construction process of the project, the relationship among the factors is complicated, and the influence of a single factor on the construction cost is difficult to determine, so that the influence on the accurate and rapid forecast of the construction cost of the forecast project is influenced; meanwhile, a large amount of data calculation work is involved in the process of collecting construction cost pricing based on data, construction cost personnel need to perform element cost superposition and dynamic analysis of the whole construction cost process under the requirement of comprehensive construction cost management, the working difficulty of the personnel is increased, although construction cost information is managed in an artificial intelligence mode to reduce the working difficulty, the traditional construction cost is mainly completed by the construction cost personnel, construction cost software, the price of the local area and other information, dynamic updating and real-time comparison cannot be realized in the calculation process, a decision basis cannot be accurately provided, highly-associated indexes influencing construction cost cannot be effectively selected, and the construction cost process data analysis capability is reduced, so a visual construction cost data prediction intelligent analysis system is needed to solve the problems.
Disclosure of Invention
The invention aims to overcome the defect and the problem of low cost process data analysis capability in the prior art, and provides a visual cost data prediction intelligent analysis system with high cost process data analysis capability.
In order to achieve the above purpose, the technical solution of the invention is as follows: a visual cost data prediction intelligent analysis system comprises a data acquisition system, a data verification module, a data intelligent processing unit, a BIM calculation unit, a neural network prediction unit and an analysis decision unit, wherein the data intelligent processing unit comprises an artificial intelligent database module and an intelligent item ranking module;
the output end of the data acquisition system is connected with the input end of the data verification module, the output end of the data verification module is connected with the input end of the artificial intelligent database module, the output end of the artificial intelligent database module is connected with the input end of the intelligent item ranking module, the output end of the intelligent item ranking module is connected with the input end of the BIM calculation unit, the output end of the BIM calculation unit is connected with the input end of the analysis decision-making unit, the input end of the neural network prediction unit is connected with the output end of the data acquisition system, and the output end of the neural network prediction unit is connected with the input end of the analysis decision-making unit;
the data checking module is used for checking the logic calculation of the data transmitted by the data acquisition system and the correctness of the data format;
the artificial intelligence database module is used for analyzing and processing mass data by adopting an artificial intelligence parallel algorithm, supporting the expansion of distributed data from a single machine to a cluster, carrying out standardized arrangement on the imported data, being compatible with a pricing file format and supporting the import of a pricing file, a contract and a drawing file in the whole process;
the intelligent listing module is used for importing a BIM (building information modeling) model by using an intelligent data interface, receiving the geometric and spatial physical attributes and the calculation relation of the project model, loading calculation rules, constructing engineering quantities, simultaneously carrying out intelligent listing by using digitization and graphic processing technologies, extracting component information in the BIM model, intelligently matching a database with BIM model component list items, assigning component item code determination, project name drafting, metering unit selection, engineering quantity calculation and project characteristic description, and realizing intelligent and standardized listing compilation;
the BIM calculation unit is used for integrating BIM models in different stages with project pricing basis and large project cost data to perform intelligent calculation quantity pricing, finding information matched with the description of the project quantity list in an artificial intelligent database during pricing, selecting unit projects needing pricing and pricing basis, setting pricing mode, intelligently reading database information and matching optimal market quotations;
the neural network prediction unit is used for establishing a BP artificial neural network model and predicting the construction cost of the project;
and the analysis decision unit is used for setting boundary conditions for the data of estimation, approximate calculation, budget, settlement and final calculation, and displaying decision suggestions through a visual graph after the boundary conditions are triggered by the data.
The data acquisition system comprises an element price collection module, an engineering information collection module and an industry dynamic collection module, and the data acquisition system collects and summarizes original data generated in the whole process of project construction through self-adaptive acquisition machine equipment, and then automatically analyzes the data to complete the acquisition and integration of cost estimation data.
The system also comprises a screening matching module, wherein the input end of the screening matching module is respectively connected with the data acquisition system and the intelligent item ranking module, and the output end of the screening matching module is connected with the input end of the neural network prediction unit;
the screening matching module is specifically configured to perform the following steps:
s1, collecting procedure data corresponding to each construction procedure, extracting each construction cost basic data sample, and performing description statistics on the collected sample data, wherein the description statistics includes the average value and the standard deviation range of the statistical sample data;
s2, extracting a sample data as an abnormal data, and calculating a mean value and a standard deviation of all sample data excluding the extracted abnormal data, wherein the mean value and the standard deviation are calculated as follows:
in the above formula, YiThe method comprises the steps of sampling the ith sample data, wherein the 10 th sample data is suspicious data, m is a mean value, L is a standard deviation, and k is the number of the sample data;
s3, judging whether the suspicious data exceed the upper limit of the confidence interval, and if so, screening the suspicious data as abnormal data;
and S4, repeating the steps from S1 to S3 on other sample data, screening all the sample data, and performing matching judgment on the process construction influence factors through the data values.
The artificial intelligence database module is used for accumulating and maintaining data through a cloud + Internet of things + intelligent terminal information technology, multiplexing, annotating and sharing the data based on cloud data, and supporting multi-entrance access of a web end and a mobile end.
The intelligent item listing module is specifically configured to perform the following steps:
s1, extracting the cost information data, including the process data corresponding to each construction process, and coding into GiDetermining machining characteristics and constructorsCorrespondence between orders:
in the above formula, GUOptimizing the values for the process data, GnnFor a restrictive process column entry matrix, GnI is the total number of processes, i is the number of standard sample processes;
and S2, initializing basic parameters, setting cycle times and repeatedly substituting the sample capacity of the sequence items, and obtaining results to compile a list.
The BIM calculation unit is specifically configured to perform the following steps:
s1, according to the list item list data of each construction process acquired by the intelligent list item module, taking the weighted average of each process parameter to obtain the weight coefficient A of the list item list of the feasible processesiAnd determining the total weight A corresponding to each process list item listl totalThe calculation formula is as follows:
s2, obtaining the optimized value Gu of the current process data-1And adjacent process data optimization value Gu-2The data difference between the two process sequences obtains the column item weight B of the current processu0；
S3, obtaining the optimized value Gu of the current process data-1Optimized value Gu of the data of the most advanced sequence process-0The distance weight B of the current process column item weight at the position of the top sequence process is obtained according to the data difference between the twoup；
S4, determining the optimized value weight A of each process datal TotalMatching the value and the group price index weight PO value with the optimal market quotation information according to the group price index weight PO value;
PO＝Buo+Bup+Al Total。
The analysis decision unit comprises a technical-economic analysis module, and the technical-economic analysis module is specifically used for executing the following steps:
firstly, matching the optimal market quotation information according to the group price index weight PO value, determining the total amount of capital flow, and then establishing a current quotation index system (KM)1、KM2、…、KMn) Historical quotation index system (KL)1、KL2、…、KLn) Then calculating the economic level correlation value KL of the current nodeGeneral assemblyValue KL associated with economic level of historical nodeTotal-1：
The analysis decision unit further comprises an intelligent decision module, and the intelligent decision module is used for executing the following steps:
firstly, the economic level correlation value KL of the current node is passedGeneral assemblyValue KL associated with economic level of historical nodeTotal-1Obtaining a difference value delta t, generating each economic control index of the project by the difference value delta t, and respectively using (JY1、JY2、…、JYn) Expressing, generating different pre-selection schemes according to a project cost index library, matching the additional investment recovery period T with each economic control index of the project, and determining a final optimization scheme;
the additional investment recovery period T is as follows:
in the above formula, I1、I2For different investment schemes, C1、C2For the annual production costs of the different solutions, Δ I is the additional investment amount and Δ C is the saved annual production cost amount.
The BP artificial neural network model adopts a fuzzy mathematics method to preferably select a training sample and a test sample, and simultaneously adopts the following two processing modes to process the sample data:
(1) the linear transformation formula is:
in the above formula, XmaxIs the maximum value of the input vector, XminIs the minimum value of the input vector;
(2) the normal transformation formula is:
in the above formula, X is the input vector, y is the output vector,
is the sample mean and σ is the sample standard deviation.
The system also comprises a supervision management unit, wherein the input end of the supervision management unit is connected with the output end of the analysis decision unit, the supervision management unit comprises a manufacturing cost data supervision management module, a manufacturing cost consultation enterprise integrity module and a manufacturing cost practitioner integrity module, and the supervision management unit is used for supervising and managing the manufacturing cost data, the data working process and the project implementation program and establishing a manufacturing cost industry integrity database and a violation enterprise and personnel blacklist database.
Compared with the prior art, the invention has the beneficial effects that:
1. in the visualized construction cost data prediction intelligent analysis system, the analysis decision unit is used for modeling and indexing complete construction cost element information stored in the database, and carrying out technical and economic index analysis, optimization and decision on the estimation, approximate calculation, budget, settlement and settlement processes, so that the intellectualization of construction cost management is improved through the application of big data and an intelligent algorithm, and data association of technical and economic levels on different time nodes is established, thereby realizing the whole process, real-time and dynamic comparative analysis and early warning, reflecting the real state of construction cost.
2. In the intelligent analysis system for the visual construction cost data prediction, a BP artificial neural network model is established through the application of a neural network prediction unit and is used for controlling the accuracy of construction cost estimation, the BP artificial neural network model needs related workers to input information parameters, then comprehensive calculation is carried out on each part of nerves, so that the most accurate and optimal result is obtained, the training error value, the sample error value, the error rate, the predicted value and the actual value are obtained, the complex nonlinear mapping between the construction cost and the main influence factors is realized through the BP neural network, and the construction cost prediction is carried out on the engineering by using the established model; meanwhile, the prediction accuracy of the established model is verified by comparing the actual value with the predicted value, so that the method has good prediction accuracy, provides a reliable basis for decision making, and has strong theoretical value and practical significance.
Drawings
Fig. 1 is a schematic structural view of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following description and embodiments in conjunction with the accompanying drawings.
Referring to fig. 1, a visual cost data prediction intelligent analysis system comprises a data acquisition system, a data check module, a data intelligent processing unit, a BIM calculation unit, a screening matching module, a neural network prediction unit, an analysis decision unit and a supervision management unit, wherein the data intelligent processing unit comprises an artificial intelligent database module and an intelligent list module; the output end of the data acquisition system is connected with the input end of the data checking module, the output end of the data checking module is connected with the input end of the artificial intelligent database module, the output end of the artificial intelligent database module is connected with the input end of the intelligent item ranking module, the output end of the intelligent item ranking module is connected with the input end of the BIM calculation unit, the output end of the BIM calculation unit is connected with the input end of the analysis decision unit, the input end of the neural network prediction unit is connected with the output end of the data acquisition system, the output end of the neural network prediction unit is connected with the input end of the analysis decision unit, the input end of the screening matching module is respectively connected with the data acquisition system and the intelligent item ranking module, the output end of the screening matching module is connected with the input end of the neural network prediction unit, and the input end of the supervision management unit is connected with the output end of the analysis decision unit.
The data acquisition system comprises an element price collection module, an engineering information collection module and an industry dynamic collection module, and the data acquisition system collects and summarizes original data generated in the whole process of project construction through self-adaptive acquisition machine equipment, and then automatically analyzes the data to complete the acquisition and integration of cost estimation data.
And the data checking module is used for checking the logic calculation of the data transmitted by the data acquisition system and the correctness of the data format.
The artificial intelligence database module is used for analyzing and processing mass data by adopting an artificial intelligence parallel algorithm, supporting the expansion of distributed data from a single machine to a cluster, carrying out standardized arrangement on the imported data, being compatible with a pricing file format and supporting the import of a pricing file, a contract and a drawing file in the whole process; the cloud-based mobile terminal data management system is further used for accumulating and maintaining data through a cloud + Internet of things + intelligent terminal information technology, multiplexing, annotating and sharing the data based on cloud data, and supporting multi-entrance access of a web end and a mobile end.
The intelligent listing module is used for importing a BIM (building information modeling) model by using an intelligent data interface, receiving the geometric and spatial physical attributes and the calculation relation of the project model, loading calculation rules, constructing engineering quantities, simultaneously carrying out intelligent listing by using digitization and graphic processing technologies, extracting component information in the BIM model, intelligently matching a database with BIM model component list items, assigning component item code determination, project name drafting, metering unit selection, engineering quantity calculation and project characteristic description, and realizing intelligent and standardized listing compilation;
the intelligent item listing module is specifically configured to perform the following steps:
s1, extracting the cost information data, including the process data corresponding to each construction process, and coding the data into GiAnd determining the corresponding relation between the machining characteristics and the construction procedures:
in the above formula, GUOptimizing the values for the process data, GnnFor a restrictive process column entry matrix, GnI is the total number of processes, i is the number of standard sample processes;
and S2, initializing basic parameters, setting cycle times and repeatedly substituting the sample capacity of the sequence items, and obtaining results to compile a list.
The screening matching module is used for inputting basic engineering parameter information of an engineering project needing cost management, extracting construction procedures in the basic engineering parameter information, and procedure basic information and procedure construction influence factors corresponding to the construction procedures, and sending the input basic engineering parameter information of the engineering project to the neural network prediction unit; the screening matching module screens data, a standard value and an error range are set in each category of the manufacturing cost through the standard value setting module, each data is compared with the standard value, the data with a larger difference range between a comparison result and the standard value is screened out through the screening module, effective manufacturing cost data are selected, the data can clearly reflect the change condition of the manufacturing cost of the project, and the workload of data processing personnel can be effectively reduced;
the screening matching module is specifically configured to perform the following steps:
s1, collecting procedure data corresponding to each construction procedure, extracting each construction cost basic data sample, and performing description statistics on the collected sample data, wherein the description statistics includes the average value and the standard deviation range of the statistical sample data;
s2, extracting a sample data as an abnormal data, and calculating a mean value and a standard deviation of all sample data excluding the extracted abnormal data, wherein the mean value and the standard deviation are calculated as follows:
in the above formula, YiThe method comprises the steps of sampling the ith sample data, wherein the 10 th sample data is suspicious data, m is a mean value, L is a standard deviation, and k is the number of the sample data;
s3, judging whether the suspicious data exceed the upper limit of the confidence interval, and if so, screening the suspicious data as abnormal data;
and S4, repeating the steps from S1 to S3 on other sample data, screening all the sample data, and performing matching judgment on the process construction influence factors through the data values.
The BIM calculation unit is used for integrating BIM models in different stages with project pricing basis and large project cost data to perform intelligent calculation quantity pricing, finding information matched with the description of the project quantity list in an artificial intelligent database during pricing, selecting unit projects needing pricing and pricing basis, setting pricing mode, intelligently reading database information and matching optimal market quotations;
the BIM calculation unit is specifically configured to perform the following steps:
s1, according to the list item list data of each construction process acquired by the intelligent list item module, taking the weighted average of each process parameter to obtain the weight coefficient A of the list item list of the feasible processesiAnd determining the total weight A corresponding to each process list item listl TotalThe calculation formula is as follows:
s2, obtaining the optimized value Gu of the current process data-1And adjacent process data optimization value Gu-2The data difference between the two processes obtains the column item weight B of the current processu0；
S3, obtaining the optimized value Gu of the current process data-1Optimized value Gu of the data of the most advanced sequence process-0The distance weight B of the current process column item weight at the position of the top sequence process is obtained according to the data difference between the twoup；
S4, determining the optimized value weight A of each process datal TotalMatching the value and the group price index weight PO value with the optimal market quotation information according to the group price index weight PO value;
PO＝Buo+Bup+Al Total。
The neural network prediction unit is used for establishing a BP artificial neural network model and predicting the construction cost of the project; the BP artificial neural network model can be divided into an input layer design, an output layer design and a hidden layer design; the input vector of each sub-model of the project can be determined in the input layer design, the output vector of the sub-model can be determined in the output layer design, and different node data can be obtained through testing the number of nodes of the hidden layer in the hidden layer design;
the BP artificial neural network model adopts a fuzzy mathematic method to preferably select a training sample and a test sample, and simultaneously, as the sample has great difference in the magnitude order of each component and the neural network algorithm requires that input and output data are in a [0, 1] interval, the sample data are processed by adopting the following two processing modes:
(1) the linear transformation formula is:
in the above formula, XmaxIs the maximum value of the input vector, XminIs input intoA minimum value of the amount;
(2) the normal transformation formula is:
in the above formula, X is the input vector, y is the output vector,
is the sample mean, σ is the sample standard deviation;
according to a fuzzy optimization rule of samples, sorting from large to small according to closeness, selecting 10 groups of data with the largest closeness as training samples for the next training, preferably selecting 10 groups of training samples, deleting data with larger difference, enabling the preferred samples to be closer to a project to be estimated, improving the prediction precision of a model, determining the number of hidden layers according to an empirical formula, selecting the first 7 training samples and the last 3 training samples from the preferred samples after data preprocessing, inputting the training samples into a program of a training network, training for multiple times, determining the best number of hidden layers, finding out that the neural network error of the number of hidden layer neurons A is the smallest through testing the number of hidden layer nodes, having the best approximation effect, enabling the neural network error of hidden layer B neurons to be very close to the neural network of the number of hidden layer C, and selecting the principle of few neural networks when the errors are close, determining the optimal number of nodes of the hidden layer as Y;
after the network training is finished, another group of detection samples are required to be used for testing the network, the output of the network is obtained by utilizing a simulation function, whether the error between the output and an actual measurement value meets the requirement or not is checked, the error rate of the detection sample can be obtained, the error of each index output can be basically controlled within 30%, the error can meet the error requirements of a project investment opportunity research stage and a preliminary feasibility research stage, and the trained neural network is used for carrying out cost valuation prediction on the project to be evaluated;
the BP artificial neural network model needs related workers to input information parameters, then comprehensive calculation is carried out on all parts of nerves, the most accurate and optimized result is obtained, the training error value, the sample error value, the error rate, the predicted value and the actual value can be obtained, complex nonlinear mapping between the engineering cost and main influence factors is realized by applying the BP neural network, the cost of the engineering is predicted by using the established model, and then the prediction precision of the established model is verified by comparing the actual value with the predicted value.
The analysis decision unit is used for setting boundary conditions for data of estimation, approximate calculation, budget, settlement and final calculation, and displaying decision suggestions through a visual graph after the boundary conditions are triggered by the data;
the analysis decision unit comprises a technical and economic analysis module, wherein the technical and economic analysis module is used for establishing data association of technical and economic levels on different time nodes by taking a platform database as a basis, taking fund motion as a main line and taking approximate calculation as a general target, so that the whole process, real-time and dynamic comparative analysis and early warning are realized, the real state of the engineering cost is reflected, the transformation from post analysis to in-process or in-advance control and from passive over-excess (settlement over-budget, budget over-approximate calculation and approximate calculation over-estimation) to active management and control is realized, and the problems of timeliness, accuracy and effectiveness of the engineering cost process control are solved; the technical-economic analysis module is specifically used for executing the following steps:
firstly, matching the optimal market quotation information according to the group price index weight PO value, determining the total amount of capital flow, and then establishing a current quotation index system (KM)1、KM2、…、KMn) Historical quotation index system (KL)1、KL2、…、KLn) Then calculating the economic level correlation value KL of the current nodeGeneral assemblyValue KL associated with economic level of historical nodeTotal-1：
The analysis decision unit further comprises an intelligent decision module, and the intelligent decision module is used for executing the following steps:
firstly, the economic level correlation value KL of the current node is passedGeneral (1)Value KL associated with economic level of historical nodeTotal-1Obtaining a difference value delta t, generating each economic control index of the project by the difference value delta t, and respectively using (JY1、JY2、…、JYn) Expressing, generating different pre-selection schemes according to a project cost index library, matching the additional investment recovery period T with each economic control index of the project, and determining a final optimization scheme;
the additional investment recovery period T is as follows:
in the above formula, I1、I2For different investment schemes, C1、C2For the annual production costs of the different solutions, Δ I is the additional investment amount and Δ C is the saved annual production cost amount.
The monitoring management unit comprises a manufacturing cost data monitoring management module, a manufacturing cost consultation enterprise integrity module and a manufacturing cost practitioner integrity module, and is used for monitoring and managing the manufacturing cost data, the data workflow and the project implementation program, and establishing a manufacturing cost industry integrity database and a violation enterprise and personnel blacklist database.
Claims (10)
1. A visual cost data prediction intelligent analysis system is characterized by comprising a data acquisition system, a data verification module, a data intelligent processing unit, a BIM calculation unit, a neural network prediction unit and an analysis decision unit, wherein the data intelligent processing unit comprises an artificial intelligent database module and an intelligent list module;
the output end of the data acquisition system is connected with the input end of the data verification module, the output end of the data verification module is connected with the input end of the artificial intelligent database module, the output end of the artificial intelligent database module is connected with the input end of the intelligent item ranking module, the output end of the intelligent item ranking module is connected with the input end of the BIM calculation unit, the output end of the BIM calculation unit is connected with the input end of the analysis decision-making unit, the input end of the neural network prediction unit is connected with the output end of the data acquisition system, and the output end of the neural network prediction unit is connected with the input end of the analysis decision-making unit;
the data checking module is used for checking the logic calculation of the data transmitted by the data acquisition system and the correctness of the data format;
the artificial intelligence database module is used for analyzing and processing mass data by adopting an artificial intelligence parallel algorithm, supporting the expansion of distributed data from a single machine to a cluster, carrying out standardized arrangement on the imported data, being compatible with a pricing file format and supporting the import of a pricing file, a contract and a drawing file in the whole process;
the intelligent listing module is used for importing a BIM (building information modeling) model by using an intelligent data interface, receiving the geometric and spatial physical attributes and the calculation relation of the project model, loading calculation rules, constructing engineering quantities, simultaneously carrying out intelligent listing by using digitization and graphic processing technologies, extracting component information in the BIM model, intelligently matching a database with BIM model component list items, assigning component item code determination, project name drafting, metering unit selection, engineering quantity calculation and project characteristic description, and realizing intelligent and standardized listing compilation;
the BIM calculation unit is used for integrating BIM models in different stages with project pricing basis and large project cost data to perform intelligent calculation quantity pricing, finding information matched with the description of the project quantity list in an artificial intelligent database during pricing, selecting unit projects needing pricing and pricing basis, setting pricing mode, intelligently reading database information and matching optimal market quotations;
the neural network prediction unit is used for establishing a BP artificial neural network model and predicting the construction cost of the project;
and the analysis decision unit is used for setting boundary conditions for the data of estimation, approximate calculation, budget, settlement and final calculation, and displaying decision suggestions through a visual graph after the boundary conditions are triggered by the data.
2. The system of claim 1, wherein the system comprises: the data acquisition system comprises an element price collection module, an engineering information collection module and an industry dynamic collection module, and the data acquisition system collects and summarizes original data generated in the whole process of project construction through self-adaptive acquisition machine equipment, and then automatically analyzes the data to complete the acquisition and integration of cost estimation data.
3. The system of claim 1, wherein the system comprises: the system also comprises a screening matching module, wherein the input end of the screening matching module is respectively connected with the data acquisition system and the intelligent item ranking module, and the output end of the screening matching module is connected with the input end of the neural network prediction unit;
the screening matching module is specifically configured to perform the following steps:
s1, collecting procedure data corresponding to each construction procedure, extracting each construction cost basic data sample, and performing description statistics on the collected sample data, wherein the description statistics includes the average value and the standard deviation range of the statistical sample data;
s2, extracting a sample data as an abnormal data, and calculating a mean value and a standard deviation of all sample data excluding the extracted abnormal data, wherein the mean value and the standard deviation are calculated as follows:
in the above formula, YiThe method comprises the steps of sampling the ith sample data, wherein the 10 th sample data is suspicious data, m is a mean value, L is a standard deviation, and k is the number of the sample data;
s3, judging whether the suspicious data exceeds the upper limit of the confidence interval, and if so, screening the suspicious data as abnormal data;
and S4, repeating the steps from S1 to S3 on other sample data, screening all the sample data, and performing matching judgment on the process construction influence factors through the data values.
4. The system of claim 1, wherein the system comprises: the artificial intelligence database module is used for accumulating and maintaining data through a cloud + Internet of things + intelligent terminal information technology, multiplexing, annotating and sharing the data based on cloud data, and supporting multi-entrance access of a web end and a mobile end.
5. The system of claim 1, wherein the system comprises: the intelligent item listing module is specifically configured to perform the following steps:
s1, extracting the cost information data, including the process data corresponding to each construction process, and coding the data into GiAnd determining the corresponding relation between the machining characteristics and the construction procedures:
in the above formula, GUOptimizing the values for the process data, GnnFor a restrictive process column entry matrix, GnI is the total number of processes, i is the number of standard sample processes;
and S2, initializing basic parameters, setting cycle times and repeatedly introducing the sample capacity of the sequence items, and obtaining results to compile a list.
6. The system of claim 5, wherein the system comprises: the BIM calculation unit is specifically configured to perform the following steps:
s1, according to the list item list data of each construction process acquired by the intelligent list item module, taking the weighted average of each process parameter to obtain the weight coefficient A of the list item list of the feasible processesiAnd determining the total weight A corresponding to each process list item listl TotalThe calculation formula is as follows:
s2, obtaining the optimized value Gu of the current process data-1And adjacent process data optimization value Gu-2The data difference between the two processes obtains the column item weight B of the current processu0；
S3, obtaining the optimized value Gu of the current process data-1Optimized value Gu of the data of the most advanced sequence process-0The distance weight B of the current process column item weight at the position of the top sequence process is obtained according to the data difference between the twoup；
S4, determining the optimized value weight A of each process datal TotalMatching the value and the group price index weight PO value with the optimal market quotation information according to the group price index weight PO value;
PO＝Buo+Bup+Al Total。
7. The system of claim 6, wherein the system comprises: the analysis decision unit comprises a technical-economic analysis module, and the technical-economic analysis module is specifically used for executing the following steps:
firstly, matching the optimal market quotation information according to the group price index weight PO value, determining the total amount of capital flow, and then establishing a current quotation index system (KM)1、KM2、…、KMn) Historical quotation index system (KL)1、KL2、…、KLn) Then calculating the economic level correlation value KL of the current nodeGeneral assemblyAssociating a value KK with a historical node economic levelTotal-1：
8. The system of claim 7, wherein the system comprises: the analysis decision unit further comprises an intelligent decision module, and the intelligent decision module is used for executing the following steps:
firstly, the economic level correlation value KL of the current node is passedGeneral assemblyValue KL associated with economic level of historical nodeTotal-1Obtaining a difference value delta t, generating each economic control index of the project by the difference value delta t, and respectively using (JY1、JY2、…、JYn) Expressing, generating different pre-selection schemes according to a project cost index library, matching the additional investment recovery period T with each economic control index of the project, and determining a final optimization scheme;
the additional investment recovery period T is as follows:
in the above formula, I1、I2For different investment schemes, C1、C2For the annual production costs of the different solutions, Δ I is the additional investment amount and Δ C is the saved annual production cost amount.
9. The system of claim 1, wherein the system comprises: the BP artificial neural network model adopts a fuzzy mathematics method to preferably select a training sample and a test sample, and simultaneously adopts the following two processing modes to process the sample data:
(1) the linear transformation formula is:
in the above formula, XmaxIs the maximum value of the input vector, XminIs the minimum value of the input vector;
(2) the normal transformation formula is:
in the above formula, X is the input vector, y is the output vector,
is the sample mean and σ is the sample standard deviation.
10. The system of claim 1, wherein the system comprises: the system also comprises a supervision management unit, wherein the input end of the supervision management unit is connected with the output end of the analysis decision unit, the supervision management unit comprises a manufacturing cost data supervision management module, a manufacturing cost consultation enterprise integrity module and a manufacturing cost practitioner integrity module, and the supervision management unit is used for supervising and managing the manufacturing cost data, the data working process and the project implementation program and establishing a manufacturing cost industry integrity database and a violation enterprise and personnel blacklist database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210034764.7A CN114548494A (en) | 2022-01-13 | 2022-01-13 | Visual cost data prediction intelligent analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210034764.7A CN114548494A (en) | 2022-01-13 | 2022-01-13 | Visual cost data prediction intelligent analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114548494A true CN114548494A (en) | 2022-05-27 |
Family
ID=81671149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210034764.7A Pending CN114548494A (en) | 2022-01-13 | 2022-01-13 | Visual cost data prediction intelligent analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114548494A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115379308A (en) * | 2022-07-19 | 2022-11-22 | 环球数科集团有限公司 | Internet of things equipment data acquisition system based on satellite remote communication |
| CN117670256A (en) * | 2024-01-28 | 2024-03-08 | 江苏建科工程咨询有限公司 | BIM technology-based engineering cost accurate control system and method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007334855A (en) * | 2006-05-17 | 2007-12-27 | Nagaoka Univ Of Technology | Schedule preparation method, schedule preparation device, and computer program |
| CN105989546A (en) * | 2016-04-13 | 2016-10-05 | 国网吉林省电力有限公司经济技术研究院 | Power transmission and transformation construction cost basic data collection and analysis system |
| US20170308934A1 (en) * | 2016-04-22 | 2017-10-26 | Economy Research Institute of State Grid Zhejiang Electric Power | Management method of power engineering cost |
| WO2019021300A1 (en) * | 2017-07-25 | 2019-01-31 | Arth Designbuild India Pvt. Ltd. | System and method for managing resources in a worksite |
| CN112016755A (en) * | 2020-08-31 | 2020-12-01 | 国网甘肃省电力公司建设分公司 | Construction method of universal design cost standardization technology module of power transmission and transformation project construction drawing |
| KR102198322B1 (en) * | 2020-08-20 | 2021-01-04 | 플레인브레드 주식회사 | Intelligent data visualization system using machine learning |
| CN112507442A (en) * | 2021-02-02 | 2021-03-16 | 巧夺天宫（深圳）科技有限公司 | BIM project material and engineering cost statistical method |
-
2022
- 2022-01-13 CN CN202210034764.7A patent/CN114548494A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007334855A (en) * | 2006-05-17 | 2007-12-27 | Nagaoka Univ Of Technology | Schedule preparation method, schedule preparation device, and computer program |
| CN105989546A (en) * | 2016-04-13 | 2016-10-05 | 国网吉林省电力有限公司经济技术研究院 | Power transmission and transformation construction cost basic data collection and analysis system |
| US20170308934A1 (en) * | 2016-04-22 | 2017-10-26 | Economy Research Institute of State Grid Zhejiang Electric Power | Management method of power engineering cost |
| WO2019021300A1 (en) * | 2017-07-25 | 2019-01-31 | Arth Designbuild India Pvt. Ltd. | System and method for managing resources in a worksite |
| KR102198322B1 (en) * | 2020-08-20 | 2021-01-04 | 플레인브레드 주식회사 | Intelligent data visualization system using machine learning |
| CN112016755A (en) * | 2020-08-31 | 2020-12-01 | 国网甘肃省电力公司建设分公司 | Construction method of universal design cost standardization technology module of power transmission and transformation project construction drawing |
| CN112507442A (en) * | 2021-02-02 | 2021-03-16 | 巧夺天宫（深圳）科技有限公司 | BIM project material and engineering cost statistical method |
Non-Patent Citations (6)
| Title |
|---|
| HAN, LH: "Research on Construction Engineering Cost Management Based on BIM Technology", 2018 3RD INTERNATIONAL CONFERENCE ON SMART CITY AND SYSTEMS ENGINEERING (ICSCSE), 14 June 2019 (2019-06-14), pages 214 - 217 * |
| 李阿勇: "电网工程建设项目现场物流管理关键问题研究", 《中国博士学位论文全文数据库 信息科技辑 (月刊)》, no. 8, 15 August 2016 (2016-08-15), pages 140 - 25 * |
| 梁敏: "公路工程建设项目施工阶段的集成成本控制探讨", 《科技信息(科学教研)》, no. 14, 10 May 2008 (2008-05-10), pages 67 * |
| 王琼: "人工智能工程造价信息管理平台构建研究", 《建筑经济》, vol. 41, no. 10, 5 October 2020 (2020-10-05), pages 69 - 72 * |
| 胡秀茂等: "基于BIM的工程造价管理应用研究", 《工程造价管理》, no. 05, 10 October 2016 (2016-10-10), pages 89 - 92 * |
| 陈宇迪: "基于MATLAB和AutoCAD二次开发的抗滑桩优化设计及可视化", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑 (月刊)》, no. 8, 15 August 2020 (2020-08-15), pages 038 - 642 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115379308A (en) * | 2022-07-19 | 2022-11-22 | 环球数科集团有限公司 | Internet of things equipment data acquisition system based on satellite remote communication |
| CN115379308B (en) * | 2022-07-19 | 2023-01-13 | 环球数科集团有限公司 | Internet of things equipment data acquisition system based on satellite remote communication |
| CN117670256A (en) * | 2024-01-28 | 2024-03-08 | 江苏建科工程咨询有限公司 | BIM technology-based engineering cost accurate control system and method |
| CN117670256B (en) * | 2024-01-28 | 2024-04-26 | 江苏建科工程咨询有限公司 | BIM technology-based engineering cost accurate control system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523316A (en) | The automation modeling method of commerce services model | |
| CN111695731B (en) | Load prediction method, system and equipment based on multi-source data and hybrid neural network | |
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN111639783A (en) | Line loss prediction method and system based on LSTM neural network | |
| CN112508053A (en) | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| US20220327398A1 (en) | Technology maturity judgment method and system based on science and technology data | |
| CN117290462B (en) | Intelligent decision system and method for large data model | |
| CN108491991A (en) | Constraints analysis system based on the industrial big data product duration and method | |
| CN112861436A (en) | Real-time prediction method for engine emission | |
| CN114119110A (en) | Project cost list collection system and method thereof | |
| CN112241606A (en) | Cooperative decision-making method for operation and maintenance of ship intelligent equipment based on CPS decision-making module | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| CN115718472A (en) | Fault scanning and diagnosing method for hydroelectric generating set | |
| CN112184412A (en) | Modeling method, device, medium and electronic equipment of credit rating card model | |
| CN110781206A (en) | Method for predicting whether electric energy meter in operation fails or not by learning meter-dismantling and returning failure characteristic rule | |
| CN117371933A (en) | Intelligent laboratory management system based on Internet of things | |
| Elwakil | Knowledge discovery based simulation system in construction | |
| CN116187932A (en) | Information system engineering supervision project risk self-adaptive assessment method | |
| CN115689331A (en) | Power transmission and transformation project quantity rationality analysis method based on MLP | |
| CN113205274A (en) | Quantitative ranking method for construction quality | |
| CN112036727A (en) | Method for positioning risk degree of gas pipeline | |
| Arakelyan et al. | Analysis of the DCS historical data for estimation of input signal significance | |
| CN107798124A (en) | Search system and method based on prediction modeling technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |